SQL-CRAFT: Text-to-SQL through Interactive Refinement and Enhanced Reasoning

arXiv:2402.14851v1 Announce Type: new
Abstract: Modern LLMs have become increasingly powerful, but they are still facing challenges in specialized tasks such as Text-to-SQL. We propose SQL-CRAFT, a framework to advance LLMs' SQL generation Capabilities through inteRActive reFinemenT and enhanced reasoning. We leverage an Interactive Correction Loop (IC-Loop) for LLMs to interact with databases automatically, as well as Python-enhanced reasoning. We conduct experiments on two Text-to-SQL datasets, Spider and Bird, with performance improvements of up to 5.7% compared to the naive …

abstract advance arxiv become capabilities challenges craft cs.ai cs.cl cs.db framework interactive llms loop modern reasoning sql sql generation tasks text text-to-sql through type